WO2022188263A1 - 一种卷烟真伪鉴别装置及方法 - Google Patents

一种卷烟真伪鉴别装置及方法 Download PDF

Info

Publication number
WO2022188263A1
WO2022188263A1 PCT/CN2021/094435 CN2021094435W WO2022188263A1 WO 2022188263 A1 WO2022188263 A1 WO 2022188263A1 CN 2021094435 W CN2021094435 W CN 2021094435W WO 2022188263 A1 WO2022188263 A1 WO 2022188263A1
Authority
WO
WIPO (PCT)
Prior art keywords
module
cigarette
microcomputer
light source
image acquisition
Prior art date
Application number
PCT/CN2021/094435
Other languages
English (en)
French (fr)
Inventor
黄星浩
谢智阳
陈瑶
梁家瑜
朱辉果
黄�俊
郭华
张天海
朱国放
程瑛
罗发亮
朱康
俞洪顺
Original Assignee
广东烟草河源市有限责任公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 广东烟草河源市有限责任公司 filed Critical 广东烟草河源市有限责任公司
Publication of WO2022188263A1 publication Critical patent/WO2022188263A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
    • G01N2021/8883—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges involving the calculation of gauges, generating models
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
    • G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques

Definitions

  • the invention relates to the field of tobacco identification equipment, and more particularly, to a device and method for authenticating cigarettes.
  • Authenticity identification of cigarettes is a core skill in the inspection of the monopoly market.
  • front-line inspectors have mainly used sensory identification methods to identify cigarettes.
  • cigarette retailers have continued to grow, and the level of cigarette counterfeiting has become higher and higher, which has brought great pressure and challenges to front-line inspectors.
  • front-line inspectors are generally equipped with law enforcement kits when they are conducting authenticity identification operations.
  • the law enforcement kits include professional law enforcement tools such as magnifying glasses, steel rulers, torches, and ultraviolet lamps, and cooperate with law enforcement tools to observe and identify tobacco one by one, which has the efficiency of identification. low problem.
  • the tools currently used in tobacco identification include the multi-functional cigarette authenticity discriminator proposed by the publication number CN203432916U (published on 2014-02-12), which is used to identify cigarettes by integrating tools such as a magnifying glass, a lighting group, and a scale. Inspectors still need to observe and identify the anti-counterfeiting identification codes one by one through ultraviolet light, and there is still a problem of low identification efficiency.
  • the present invention provides a device for authenticating cigarettes in order to overcome the defect of low efficiency of cigarette authenticity identification described in the prior art.
  • the technical scheme of the present invention is as follows:
  • a cigarette authenticity identification device comprising an image acquisition module, a microcomputer, a display module, a power supply module, and a box, a bracket, a fixed base, and an auxiliary light source, wherein the output end of the image acquisition module is connected to an output end of the microcomputer.
  • the input end is connected, and the output end of the microcomputer is connected with the input end of the display module; the output end of the power supply module is respectively electrically connected with the power supply ends of the image acquisition module, the microcomputer and the display module; the The microcomputer, the display module and the power supply module are arranged in the box; the display module is arranged on the front of the box; the bottom of the front of the box is arranged with an opening, and the fixed base is arranged on the bottom of the box; the The image acquisition module is connected and fixed in the box through the bracket and above the fixed base; the auxiliary light source is arranged in the box and below the image acquisition module.
  • the image acquisition module is used to collect cigarette images, and transmit the collected images to a microcomputer, where the authenticity identification result is obtained after being processed by a visual algorithm preset in the microcomputer.
  • the back of the box is provided with several vertically arranged fixing slots; one end of the bracket is connected and fixed with the image acquisition module, and the other end of the bracket is connected and fixed with the fixing slot by nuts and bolts .
  • the device further includes a ring-shaped light source bracket, and the auxiliary light source is arranged on the light source bracket; one end of the light source bracket is connected and fixed to the fixing groove by a nut and a bolt.
  • the device further includes a communication module, and the input end of the communication module is connected to the output end of the microcomputer.
  • the device further includes a GPS module, and the output end of the GPS module is connected to the input end of the microcomputer.
  • the microcomputer is provided with one or more of a USB interface, an HDMI interface, and a serial communication interface.
  • the device further includes a light source controller, the light source controller is connected to the microcomputer, and the output end of the light source controller is connected to the input end of the auxiliary light source.
  • the device further includes a power conversion module, the input terminal of the power conversion module is connected to the output terminal of the power supply module, and the first output terminal of the power conversion module is electrically connected to the power supply terminal of the microcomputer.
  • the second output end of the power conversion module is electrically connected to the power supply end of the light source controller.
  • the fixing base is provided with three card slots, and the slot widths of the three card slots are respectively larger than the widths of the front side, the left side and the lower side of the cigarette package.
  • the present invention also proposes a method for authenticating cigarettes, comprising the following steps:
  • the image acquisition module collects cigarette images
  • S4 Select a target discriminating algorithm from the database according to the brand classification label of the cigarette, discriminate the cigarette image, output the cigarette authenticity discrimination result, and send it to the display module for display.
  • the beneficial effects of the technical solution of the present invention are: the present invention collects cigarette images through an image acquisition module, transmits the collected images to a microcomputer, and performs authenticity identification through an image recognition method to generate authenticity of cigarettes.
  • the identification result is transmitted to the display module for display, which can effectively improve the work efficiency of tobacco identification; the present invention can effectively improve the accuracy of cigarette identification by classifying cigarette images, and selecting a corresponding identification algorithm according to the classification label to further identify the cigarette images. Rate.
  • FIG. 1 is a schematic structural diagram of the device for authenticating cigarettes according to Example 1.
  • FIG. 2 is a schematic diagram of the electrical structure of the cigarette authenticity discriminating device of Example 1.
  • FIG. 2 is a schematic diagram of the electrical structure of the cigarette authenticity discriminating device of Example 1.
  • FIG. 3 is a rear view of the cigarette authenticity discriminating device of Example 2.
  • Example 4 is a schematic diagram of a partial structure of the device for authenticating cigarettes according to Example 2.
  • FIG. 5 is a schematic diagram of the electrical structure of the cigarette authenticity discriminating device of Example 3.
  • FIG. 5 is a schematic diagram of the electrical structure of the cigarette authenticity discriminating device of Example 3.
  • FIG. 6 is a flow chart of the method for authenticating cigarettes according to Embodiment 4.
  • FIG. 7 is a flowchart of the brand A discrimination algorithm of the fourth embodiment.
  • 1-image acquisition module 2-microcomputer, 201-USB interface, 202-HDMI interface, 203-serial communication interface, 3-display module, 4-power module, 5-box, 501-handle, 502 -Fixing slot, 6-bracket, 7-fixed base, 701-card slot, 8-auxiliary light source, 9-light source bracket, 10-communication module, 11-GPS module, 12-light source controller, 13-power conversion module.
  • FIGS. 1-2 are schematic structural diagrams of the device for authenticating cigarettes in this embodiment.
  • the cigarette authenticity identification device proposed in this embodiment includes an image acquisition module 1, a microcomputer 2, a display module 3, a power supply module 4, a box body 5, a bracket 6, a fixed base 7, and an auxiliary light source 8, wherein:
  • the output end of the image acquisition module 1 is connected with the input end of the microcomputer 2, and the output end of the microcomputer 2 is connected with the input end of the display module 3; the output end of the power supply module 4 is respectively connected with the image acquisition module 1, the microcomputer 2 and the display module. 3.
  • the power supply end of the auxiliary light source 8 is electrically connected;
  • the microcomputer 2, the display module 3, and the power module 4 are arranged in the box body 5;
  • the display module 3 is arranged on the front of the box body 5;
  • the front bottom of the box body 5 is provided with an opening, and the fixed base 7 is arranged on the inner bottom of the box body 5.
  • the user can place the cigarette to be identified on the fixed base 7 inside the box body 5 through the opening provided on the front bottom of the box body 5, which is convenient for further passage.
  • the image acquisition module 1 performs image acquisition;
  • the image acquisition module 1 is connected and fixed in the box 5 through the bracket 6 and above the fixed base 7;
  • the auxiliary light source 8 is arranged in the box body 5, and the auxiliary light source 8 is arranged below the image acquisition module 1, and is used to fill light for the cigarettes placed on the fixed base 7, so as to facilitate the collection of cigarette images.
  • the fixed base 7 in this embodiment is provided with three card slots 701, and the slot widths of the three card slots 701 are respectively greater than the widths of the front side, left side and lower side of the cigarette package, and are used to place and Fixed cigarettes for easy capture of images of the outer packaging on all sides of the cigarette.
  • top of the box body 5 in this embodiment is provided with a handle 501 to facilitate the carrying of the device.
  • the image acquisition module 1 adopts an industrial camera, and the microcomputer 2 is preset with a visual algorithm for identifying the authenticity of cigarettes.
  • the microcomputer 2 adopts a NUC industrial computer.
  • the display module 3 in this embodiment adopts a touch display screen, which is used as a human-computer interaction tool to display the authenticity identification result of cigarettes and input corresponding instructions to the microcomputer 2 for execution.
  • the cigarettes to be identified are placed on the fixed base 7 inside the casing 5 through the opening provided at the bottom of the front of the casing 5, and the image acquisition module 1 collects images of the cigarettes placed on the fixed base 7, and then The collected cigarette image is transmitted to the microcomputer 2 for image recognition processing, and the microcomputer 2 sends the collected image and the identification result obtained through image recognition to the display module 3 for display for the user to view.
  • FIGS. 3 to 4 it is a schematic structural diagram of the device for authenticating cigarettes according to the present embodiment.
  • a number of vertically arranged fixing grooves 502 are formed on the back of the box body 5; The groove 502 is connected and fixed.
  • the device for discriminating the authenticity of cigarettes proposed in this embodiment further includes an annular light source bracket 9, and the auxiliary light source 8 is arranged on the light source bracket 9;
  • the light source bracket 9 is designed in a circular ring shape, which avoids blocking the image acquisition range of the image acquisition module 1, and at the same time, can fill the cigarette with light in all directions.
  • the bracket 6 connected with the image acquisition module 1 is connected and fixed to the fixing groove 502 by nuts and bolts
  • the light source bracket 9 is connected and fixed to the fixing groove 502 by using nuts and bolts.
  • the distance between the bracket 6 and the fixed base 7 adjust the height of the bracket 6 along the direction of the fixing slot 502, and then further adjust the distance between the light source bracket 9 and the bracket 6 and the fixed base 7 along the direction of the fixing slot 502.
  • the relative position of the assembly is completed, and the nut and bolt are connected and fixed with the fixing groove 502 to complete the assembly.
  • the cigarette to be identified is placed on the fixed base 7, and the image acquisition module 1 collects the image of the cigarette placed on the fixed base 7, and then transmits the collected cigarette image to the microcomputer 2 for image recognition processing.
  • the collected image and the identification result obtained through image recognition are sent to the display module 3 for display for the user to view.
  • FIG. 5 it is a schematic structural diagram of the device for authenticating cigarettes according to the present embodiment.
  • the cigarette authenticity identification device proposed in this embodiment further includes a communication module 10, a GPS module 11, a light source controller 12, and a power conversion module 13, wherein:
  • the input end of the communication module 10 is connected with the output end of the microcomputer 2;
  • the output end of the GPS module 11 is connected with the input end of the microcomputer 2;
  • the light source controller 12 is connected to the microcomputer 2, and the output end of the light source controller 12 is connected to the control end of the auxiliary light source 8;
  • the input terminal of the power conversion module 13 is connected to the output terminal of the power supply module 4 , the first output terminal of the power conversion module 13 is electrically connected to the power supply terminal of the microcomputer 2 , and the power conversion module 13
  • the second output end of the light source controller 12 is electrically connected to the power supply end of the light source controller 12 .
  • the microcomputer 2 in this embodiment is provided with a USB interface 201, an HDMI interface 202, and a serial communication interface 203, wherein the USB interface 201 is used to connect the image acquisition module 1 or the display module 3, or to communicate with external The device performs data exchange; the HDMI interface 202 is used to connect the display module 3 ; the serial communication interface 203 is used to connect the light source controller 12 .
  • the communication module 10 in this embodiment adopts one or more of a 4G module, a 5G module, a WIFI module, and a GPRS module; the communication module 10 is used to upload the collected cigarette images to the server, and gradually build a large database of cigarette images , which can be viewed by professional appraisal personnel in the background, and used to update the visual algorithm of cigarette authenticity identification to improve the identification accuracy.
  • the GPS module 11 in this embodiment is used to obtain the current position of the cigarette identification device, and upload it to the server through the communication module 10, so as to lock the sales position of counterfeit cigarettes, so as to provide relevant information to the inspectors.
  • the light source controller 12 in this embodiment is connected to the microcomputer 2 through the serial communication interface 203, and performs data transmission with the microcomputer 2 through serial communication.
  • the light source controller 12 receives the instructions sent from the microcomputer 2, and further controls the auxiliary
  • the light source type and light source brightness of the light source 8 ensure the stability of cigarette image collection.
  • the power conversion module 13 in this embodiment is used to convert the stable DC power output by the power supply module 4 to provide working power to the microcomputer 2 and the light source controller 12 respectively.
  • the cigarettes to be identified are placed on the fixed base 7 inside the casing 5 through the opening provided at the bottom of the front of the casing 5, and the image acquisition module 1 collects images of the cigarettes placed on the fixed base 7, and then The collected cigarette image is transmitted to the microcomputer 2 for image recognition processing, and the microcomputer 2 sends the collected image and the identification result obtained through image recognition to the display module 3 for display for the user to view.
  • the microcomputer 2 uploads the collected cigarette images and the corresponding identification results to the server through the communication module 10, which is used to establish a large database of cigarette images, which can be viewed by professional appraisers in the background, and used to update the cigarette authenticity identification visual algorithm. .
  • the microcomputer 2 obtains the position information of the current device through the GPS module 11, and uploads the position information to the background server through the communication module 10, so as to provide relevant information to the inspectors.
  • This embodiment provides a method for authenticating cigarettes, which is applied to the device for authenticating cigarettes proposed in any one of Embodiments 1 to 3. As shown in FIG. 6 , it is a flowchart of the method for authenticating cigarettes according to the present embodiment.
  • the image acquisition module collects cigarette images
  • S4 Select a target discriminating algorithm from the database according to the brand classification label of the cigarette, discriminate the cigarette image, output the cigarette authenticity discrimination result, and send it to the display module for display.
  • the steps of preprocessing the cigarette image include Gaussian filtering, threshold segmentation and morphological operations.
  • This embodiment illustrates an example of a discrimination algorithm for brand A, as shown in Figure 7:
  • Connectivity analysis is performed on the preprocessed cigarette image, and the ROI area is intercepted, and the histogram statistics are performed on the ROI area;

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Health & Medical Sciences (AREA)
  • Signal Processing (AREA)
  • Biophysics (AREA)
  • Analytical Chemistry (AREA)
  • Biochemistry (AREA)
  • Quality & Reliability (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • Artificial Intelligence (AREA)
  • Biomedical Technology (AREA)
  • Chemical & Material Sciences (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Inspection Of Paper Currency And Valuable Securities (AREA)

Abstract

一种卷烟真伪鉴别装置，包括图像采集模块（1）、微型计算机（2）、显示模块（3）、电源模块（4），以及箱体（5）、支架（6）、固定底座（7）、辅助光源（8），图像采集模块（1）的输出端与微型计算机（2）的输入端连接，微型计算机（2）的输出端与显示模块（3）的输入端连接；电源模块（4）的输出端分别与图像采集模块（1）、微型计算机（2）、显示模块（3）的供电端电性连接；微型计算机（2）、显示模块（3）、电源模块（4）设置在箱体（5）内；显示模块（3）设置在箱体（5）正面；箱体（5）正面底部开口设置，固定底座（7）设置在箱体（5）内底部；图像采集模块（1）经支架（6）连接固定在箱体（5）内且于固定底座（7）上方；辅助光源（8）设置在箱体（5）内且于图像采集模块（1）下方。

Description

一种卷烟真伪鉴别装置及方法 技术领域
本发明涉及烟草鉴别设备领域，更具体地，涉及一种卷烟真伪鉴别装置及方法。
背景技术
卷烟真伪鉴别是专卖市场检查的核心技能，多年来一线稽查人员主要运用感观鉴别法对卷烟进行鉴别。但是，近年来，卷烟零售户持续增长，卷烟制假水平越来越高，给一线稽查人员带来很大压力和挑战。目前一线稽查人员在进行鉴别真伪作业时，一般是配备执法包，执法包内包括放大镜、钢尺、电筒、紫外光灯等专业执法工具，配合执法工具对烟草逐一进行观察鉴别，存在鉴别效率低的问题。
目前应用于烟草鉴别的工具有如公开号为CN203432916U(公开日2014-02-12)提出的多功能卷烟真伪鉴别器，通过集成放大镜、灯光组、刻度尺等工具对卷烟进行识别，但该方案仍需稽查人员通过紫外光对防伪标识码逐一进行观察鉴别，仍然存在鉴别效率低的问题。
发明内容
本发明为克服上述现有技术所述的卷烟真伪鉴别效率低的缺陷，提供一种卷烟真伪鉴别装置。
为解决上述技术问题，本发明的技术方案如下：
一种卷烟真伪鉴别装置，包括图像采集模块、微型计算机、显示模块、电源模块，以及箱体、支架、固定底座、辅助光源，其中，所述图像采集模块的输出端与所述微型计算机的输入端连接，所述微型计算机的输出端与所述显示模块的输入端连接；所述电源模块的输出端分别与所述图像采集模块、微型计算机、显示模块的供电端电性连接；所述微型计算机、显示模块、电源模块设置在所述箱体内；所述显示模块设置在所述箱体正面；所述箱体正面底部开口设置，所述固定底座设置在所述箱体内底部；所述图像采集模块经所述支架连接固定在所述箱体内且于所述固定底座上方；所述辅助光源设置在所述箱体内且于所述图像采集 模块下方。
本技术方案中，图像采集模块用于采集卷烟图像，并将采集的图像传输至微型计算机，由微型计算机内部预设的视觉算法处理后得到真伪鉴别结果。
作为优选方案，所述箱体背面开设有若干竖直设置的固定槽；所述支架的一端与所述图像采集模块连接固定，所述支架的另一端采用螺母、螺栓与所述固定槽连接固定。
作为优选方案，所述装置还包括圆环形光源支架，所述辅助光源设置在所述光源支架上；所述光源支架的一端采用螺母、螺栓与所述固定槽连接固定。
作为优选方案，所述装置还包括通信模块，所述通信模块的输入端与所述微型计算机的输出端连接。
作为优选方案，所述装置还包括GPS模块，所述GPS模块的输出端与所述微型计算机的输入端连接。
作为优选方案，所述微型计算机中设置有USB接口、HDMI接口、串行通信接口中的一种或多种。
作为优选方案，所述装置还包括光源控制器，所述光源控制器与所述微型计算机连接，所述光源控制器的输出端与所述辅助光源的输入端连接。
作为优选方案，所述装置还包括电源转换模块，所述电源转换模块的输入端与所述电源模块的输出端连接，所述电源转换模块的第一输出端与所述微型计算机的供电端电性连接，所述电源转换模块的第二输出端与所述光源控制器的供电端电性连接。
作为优选方案，所述固定底座开设有3个卡槽，所述3个卡槽的槽宽分别大于卷烟包装正侧面、左侧面、下侧面的宽度。
本发明还提出了一种卷烟真伪鉴别方法，包括以下步骤：
S1：图像采集模块采集卷烟图像；
S2：对卷烟图像进行预处理；
S3：对经过预处理的卷烟图像输入分类算法模型，得到卷烟的品牌分类标签；
S4：根据所述卷烟的品牌分类标签从数据库中选择目标判别算法，对所述卷烟图像进行判别，输出得到卷烟真伪鉴别结果，并发送到显示模块中进行显示。
与现有技术相比，本发明技术方案的有益效果是：本发明通过图像采集模块采集卷烟图像，并将采集的图像传输至微型计算机中，通过图像识别方法进行真 伪鉴别，生成卷烟真伪鉴别结果后传输至显示模块中进行显示，能够有效提高烟草鉴别的工作效率；本发明通过对卷烟图像进行分类，并根据分类标签选择相应的判别算法对卷烟图像进一步鉴别，能够有效提高卷烟鉴别准确率。
附图说明
图1为实施例1的卷烟真伪鉴别装置的结构示意图。
图2为实施例1的卷烟真伪鉴别装置的电气结构示意图。
图3为实施例2的卷烟真伪鉴别装置的后视图。
图4为实施例2的卷烟真伪鉴别装置的局部结构示意图。
图5为实施例3的卷烟真伪鉴别装置的电气结构示意图。
图6为实施例4的卷烟真伪鉴别方法的流程图。
图7为实施例4的品牌A判别算法的流程图。
其中，1-图像采集模块，2-微型计算机，201-USB接口，202-HDMI接口，203-串行通信接口，3-显示模块，4-电源模块，5-箱体，501-把手，502-固定槽，6-支架，7-固定底座，701-卡槽，8-辅助光源，9-光源支架，10-通信模块，11-GPS模块，12-光源控制器，13-电源转换模块。
具体实施方式
附图仅用于示例性说明，不能理解为对本专利的限制；
对于本领域技术人员来说，附图中某些公知结构及其说明可能省略是可以理解的。
下面结合附图和实施例对本发明的技术方案做进一步的说明。
实施例1
本实施例提出一种卷烟真伪鉴别装置，如图1～2所示，为本实施例的卷烟真伪鉴别装置的结构示意图。
本实施例提出的卷烟真伪鉴别装置中，包括图像采集模块1、微型计算机2、显示模块3、电源模块4，以及箱体5、支架6、固定底座7、辅助光源8，其中：
图像采集模块1的输出端与微型计算机2的输入端连接，微型计算机2的输出端与显示模块3的输入端连接；电源模块4的输出端分别与图像采集模块1、微型计算机2、显示模块3、辅助光源8的供电端电性连接；
微型计算机2、显示模块3、电源模块4设置在箱体5内；
显示模块3设置在箱体5正面；
箱体5正面底部开口设置，固定底座7设置在箱体5内底部，用户可通过箱体5正面底部设置的开口将待鉴别的卷烟放置在箱体5内部的固定底座7上，便于进一步通过图像采集模块1进行图像采集；
图像采集模块1经支架6连接固定在箱体5内且于固定底座7上方；
辅助光源8设置在箱体5内，且辅助光源8设置在图像采集模块1的下方，用于对放置在固定底座7上的卷烟进行补光，便于卷烟图像采集。
进一步的，本实施例中的固定底座7开设有3个卡槽701，3个卡槽701的槽宽分别大于卷烟包装正侧面、左侧面、下侧面的宽度，用于以各个角度放置并固定卷烟，便于采集卷烟各个侧面的外包装图像。
进一步的，本实施例中的箱体5顶部设置有把手501，便于装置的携带。
本实施例中，图像采集模块1采用工业相机，微型计算机2中预设有用于鉴别卷烟真伪的视觉算法。
本实施例中，微型计算机2采用NUC工控机。
本实施例中的显示模块3采用触摸显示屏，用于作为人机交互工具，显示卷烟真伪鉴别结果以及输入相应指令至微型计算机2中执行。
在具体实施过程中，经箱体5正面底部设置的开口将待鉴别的卷烟放置在箱体5内部的固定底座7上，图像采集模块1对放置在固定底座7上的卷烟进行图像采集，然后将采集的卷烟图像传输至微型计算机2中进行图像识别处理，微型计算机2将采集的图像及经过图像识别得到的鉴别结果发送至显示模块3中进行显示，供用户查看。
实施例2
本实施例在实施例1提出的卷烟真伪鉴别装置的基础上作出改进。如图3～4所示，为本实施例的卷烟真伪鉴别装置的结构示意图。
本实施例提出的卷烟真伪鉴别装置中，箱体5背面开设有若干竖直设置的固定槽502；支架6的一端与图像采集模块1连接固定，支架6的另一端采用螺母、螺栓与固定槽502连接固定。
进一步的，本实施例提出的卷烟真伪鉴别装置还包括圆环形的光源支架9，辅助光源8设置在光源支架9上；光源支架9的一端采用螺母、螺栓与固定槽502连接固定。其中，光源支架9为圆环形设计，避免遮挡图像采集模块1的图像采集范围，同时能够全方位对卷烟进行补光。
在具体实施过程中，将连接有图像采集模块1的支架6采用螺母、螺栓与固定槽502连接固定，并将光源支架9采用螺母、螺栓与固定槽502连接固定。其中，根据实际使用需求，根据支架6与固定底座7之间的距离，沿固定槽502方向调整支架6的高度，再进一步沿固定槽502方向调整光源支架9与支架6、固定底座7之间的相对位置，并采用螺母、螺栓与固定槽502连接固定，完成组装。然后将待鉴别的卷烟放置在固定底座7上，图像采集模块1对放置在固定底座7上的卷烟进行图像采集，然后将采集的卷烟图像传输至微型计算机2中进行图像识别处理，微型计算机2将采集的图像及经过图像识别得到的鉴别结果发送至显示模块3中进行显示，供用户查看。
实施例3
本实施例在实施例1或实施例2提出的卷烟真伪鉴别装置的基础上作出改进。如图5所示，为本实施例的卷烟真伪鉴别装置的结构示意图。
本实施例提出的卷烟真伪鉴别装置中，还包括通信模块10、GPS模块11、光源控制器12、电源转换模块13，其中：
所述通信模块10的输入端与所述微型计算机2的输出端连接；
所述GPS模块11的输出端与所述微型计算机2的输入端连接；
所述光源控制器12与所述微型计算机2连接，所述光源控制器12的输出端与所述辅助光源8的控制端连接；
所述电源转换模块13的输入端与所述电源模块4的输出端连接，所述电源转换模块13的第一输出端与所述微型计算机2的供电端电性连接，所述电源转换模块13的第二输出端与所述光源控制器12的供电端电性连接。
进一步的，本实施例中的微型计算机2中设置有USB接口201、HDMI接口202、串行通信接口203，其中，USB接口201用于连接图像采集模块1或显示模块3，或用于与外部设备进行数据交互；HDMI接口202用于连接显示模块3；串行通信接口203用于连接光源控制器12。
本实施例中的通信模块10采用4G模块、5G模块、WIFI模块、GPRS模块中的一种或多种；通信模块10用于将将采集的卷烟图像上传到服务器中，逐步建立卷烟图像大数据库，供后台专业鉴定人员查看，以及用于对卷烟真伪鉴定视觉算法进行更新，提高鉴定准确率。
本实施例中的GPS模块11用于获取当前卷烟鉴别装置的位置，并通过通信 模块10上传至服务器中，用于锁定伪造卷烟销售位置，便于向稽查人员提供相关信息。
本实施例中的光源控制器12通过串行通信接口203与微型计算机2连接，通过串行通信方式与微型计算机2进行数据传输，光源控制器12接收从微型计算机2发出的指令，进一步控制辅助光源8的光源类型及光源亮度，保证卷烟图像采集的稳定性。
本实施例中的电源转换模块13用于将电源模块4输出的稳定直流电进行转换后分别给微型计算机2和光源控制器12提供工作电源。
在具体实施过程中，经箱体5正面底部设置的开口将待鉴别的卷烟放置在箱体5内部的固定底座7上，图像采集模块1对放置在固定底座7上的卷烟进行图像采集，然后将采集的卷烟图像传输至微型计算机2中进行图像识别处理，微型计算机2将采集的图像及经过图像识别得到的鉴别结果发送至显示模块3中进行显示，供用户查看。微型计算机2将采集的卷烟图像及相应的鉴别结果通过通信模块10上传到服务器中，用于建立卷烟图像大数据库，并供后台专业鉴定人员查看，以及用于对卷烟真伪鉴定视觉算法进行更新。同时，微型计算机2通过GPS模块11获取当前装置的位置信息，并通过通信模块10将位置信息上传至后台服务器中，便于向稽查人员提供相关信息。
实施例4
本实施例提出一种卷烟真伪鉴别方法，应用于实施例1～3任一提出的卷烟真伪鉴别装置。如图6所示，为本实施例的卷烟真伪鉴别方法的流程图。
本实施例提出的卷烟真伪鉴别方法中，包括以下步骤：
S1：图像采集模块采集卷烟图像；
S2：对卷烟图像进行预处理；
S3：对经过预处理的卷烟图像输入分类算法模型，得到卷烟的品牌分类标签；
S4：根据所述卷烟的品牌分类标签从数据库中选择目标判别算法，对所述卷烟图像进行判别，输出得到卷烟真伪鉴别结果，并发送到显示模块中进行显示。
本实施例中，卷烟图像进行预处理的步骤包括高斯滤波、阈值分割及形态学操作。
本实施例对一种品牌A的判别算法举例说明，如图7所示：
(1)对经过预处理的卷烟图像进行连通性分析，并截取ROI区域，对所述 ROI区域进行直方图统计；
(2)根据所述卷烟图像的直方图进行直方图谷底确定阈值法分割，得到特征图像；
(3)对所述特征图像进行形态学操作及连通性分析，从所述特征图像中提取特征向量；
(4)将所述特征向量输入神经网络模型，输出得到卷烟真伪鉴别结果。
相同或相似的标号对应相同或相似的部件；
附图中描述位置关系的用语仅用于示例性说明，不能理解为对本专利的限制；
显然，本发明的上述实施例仅仅是为清楚地说明本发明所作的举例，而并非是对本发明的实施方式的限定。对于所属领域的普通技术人员来说，在上述说明的基础上还可以做出其它不同形式的变化或变动。这里无需也无法对所有的实施方式予以穷举。凡在本发明的精神和原则之内所作的任何修改、等同替换和改进等，均应包含在本发明权利要求的保护范围之内。

Claims (10)

  1. 一种卷烟真伪鉴别装置，其特征在于，包括图像采集模块、微型计算机、显示模块、电源模块，以及箱体、支架、固定底座、辅助光源，其中：
    所述图像采集模块的输出端与所述微型计算机的输入端连接，所述微型计算机的输出端与所述显示模块的输入端连接；所述电源模块的输出端分别与所述图像采集模块、微型计算机、显示模块、辅助光源的供电端电性连接；
    所述微型计算机、显示模块、电源模块设置在所述箱体内；
    所述显示模块设置在所述箱体正面；
    所述箱体正面底部开口设置，所述固定底座设置在所述箱体内底部；
    所述图像采集模块经所述支架连接固定在所述箱体内且于所述固定底座上方；
    所述辅助光源设置在所述箱体内且于所述图像采集模块下方。
  2. 根据权利要求1所述的卷烟真伪鉴别装置，其特征在于，所述箱体背面开设有若干竖直设置的固定槽；所述支架的一端与所述图像采集模块连接固定，所述支架的另一端采用螺母、螺栓与所述固定槽连接固定。
  3. 根据权利要求2所述的卷烟真伪鉴别装置，其特征在于，所述装置还包括圆环形的光源支架，所述辅助光源设置在所述光源支架上；所述光源支架的一端采用螺母、螺栓与所述固定槽连接固定。
  4. 根据权利要求1所述的卷烟真伪鉴别装置，其特征在于，所述装置还包括通信模块，所述通信模块的输入端与所述微型计算机的输出端连接。
  5. 根据权利要求4所述的卷烟真伪鉴别装置，其特征在于，所述装置还包括GPS模块，所述GPS模块的输出端与所述微型计算机的输入端连接。
  6. 根据权利要求1所述的卷烟真伪鉴别装置，其特征在于，所述微型计算机中设置有USB接口、HDMI接口、串行通信接口中的一种或多种。
  7. 根据权利要求1所述的卷烟真伪鉴别装置，其特征在于，所述装置还包括光源控制器，所述光源控制器通过串行通信接口与所述微型计算机连接，所述光源控制器的输出端与所述辅助光源的控制端连接。
  8. 根据权利要求7所述的卷烟真伪鉴别装置，其特征在于，所述装置还包括电源转换模块，所述电源转换模块的输入端与所述电源模块的输出端连接，所 述电源转换模块的第一输出端与所述微型计算机的供电端电性连接，所述电源转换模块的第二输出端与所述光源控制器的供电端电性连接。
  9. 根据权利要求1～8任一项所述的卷烟真伪鉴别装置，其特征在于，所述固定底座开设有3个卡槽，所述3个卡槽的槽宽分别大于卷烟包装正侧面、左侧面、下侧面的宽度。
  10. 一种卷烟真伪鉴别方法，应用于权利要求1～9任一项所述的卷烟真伪鉴别装置，其特征在于，包括以下步骤：
    S1：图像采集模块采集卷烟图像；
    S2：对卷烟图像进行预处理；
    S3：对经过预处理的卷烟图像输入分类算法模型，得到卷烟的品牌分类标签；
    S4：根据所述卷烟的品牌分类标签从数据库中选择目标判别算法，对所述卷烟图像进行判别，输出得到卷烟真伪鉴别结果，并发送到显示模块中进行显示。
PCT/CN2021/094435 2021-03-08 2021-05-18 一种卷烟真伪鉴别装置及方法 WO2022188263A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110250355.6A CN112986262A (zh) 2021-03-08 2021-03-08 一种卷烟真伪鉴别装置及方法
CN202110250355.6 2021-03-08

Publications (1)

Publication Number Publication Date
WO2022188263A1 true WO2022188263A1 (zh) 2022-09-15

Family

ID=76335277

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/094435 WO2022188263A1 (zh) 2021-03-08 2021-05-18 一种卷烟真伪鉴别装置及方法

Country Status (2)

Country Link
CN (1) CN112986262A (zh)
WO (1) WO2022188263A1 (zh)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN201773069U (zh) * 2010-03-05 2011-03-23 北京紫光天禾软件系统技术有限公司 卷烟产品鉴别一体化设备
CN202453299U (zh) * 2012-01-19 2012-09-26 深圳中航信息科技产业股份有限公司 用于卷烟鉴别的远程质检一体化终端
JP2012208139A (ja) * 2011-03-29 2012-10-25 Japan Tobacco Inc ディスプレイ装置、たばこ什器、自動販売機
CN103440492A (zh) * 2013-09-05 2013-12-11 湖北省烟草公司荆州市公司 一种手持卷烟识别器
CN208400151U (zh) * 2018-07-13 2019-01-18 山东聊城烟草有限公司 智能化卷烟自动鉴别仪

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20120117049A (ko) * 2011-04-14 2012-10-24 삼성전자주식회사 휴대용 단말기에서 위조 지폐 감별 방법 및 장치
KR101142910B1 (ko) * 2011-08-01 2012-05-10 (주)댐코씨에스아이 위조지폐 감식장치
CN105181709A (zh) * 2015-10-14 2015-12-23 中国计量学院 刹车片外观缺陷组合式多光源在线检测装置及方法
CN207502429U (zh) * 2017-11-27 2018-06-15 东莞万思自动化技术开发有限公司 一种中央处理器pin针缺陷检测设备
CN110286095A (zh) * 2019-07-18 2019-09-27 黑龙江省烟草公司哈尔滨市公司 基于颜色鉴定法的便携式卷烟真伪识别系统、仪器及方法
CN111523908B (zh) * 2020-03-31 2023-04-07 云南省烟草质量监督检测站 一种鉴别卷烟真伪的包装机型溯源方法、装置及系统
CN214953088U (zh) * 2021-03-08 2021-11-30 广东烟草河源市有限责任公司 一种卷烟真伪鉴别装置

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN201773069U (zh) * 2010-03-05 2011-03-23 北京紫光天禾软件系统技术有限公司 卷烟产品鉴别一体化设备
JP2012208139A (ja) * 2011-03-29 2012-10-25 Japan Tobacco Inc ディスプレイ装置、たばこ什器、自動販売機
CN202453299U (zh) * 2012-01-19 2012-09-26 深圳中航信息科技产业股份有限公司 用于卷烟鉴别的远程质检一体化终端
CN103440492A (zh) * 2013-09-05 2013-12-11 湖北省烟草公司荆州市公司 一种手持卷烟识别器
CN208400151U (zh) * 2018-07-13 2019-01-18 山东聊城烟草有限公司 智能化卷烟自动鉴别仪

Also Published As

Publication number Publication date
CN112986262A (zh) 2021-06-18

Similar Documents

Publication Publication Date Title
EP2833288A1 (en) Face calibration method and system, and computer storage medium
CN104537651B (zh) 一种路面图像中裂缝比例检测方法及系统
CN106446926A (zh) 一种基于视频分析的变电站工人安全帽佩戴检测方法
Rasouli et al. The effect of color space selection on detectability and discriminability of colored objects
CN111402224B (zh) 一种用于电力设备的目标识别方法
Boucher et al. Development of a semi-automatic system for pollen recognition
CN107341688A (zh) 一种客户体验的采集方法及系统
CN103440035A (zh) 一种三维空间中的手势识别系统及其识别方法
CN106228157B (zh) 基于图像识别技术的彩色图像文字段落分割与识别方法
CN102095731A (zh) 在纸张缺陷视觉检测中识别不同缺陷类型的系统及方法
CN107977639A (zh) 一种人脸清晰度判断方法
CN104331710A (zh) 开关状态识别系统
CN109670449B (zh) 一种基于垂直抓拍方式的车辆违法判断方法
CN110796372A (zh) 一种工业企业安全生产风险辨识系统及其方法
CN104198497A (zh) 一种基于视觉显著图和支持向量机的表面缺陷检测方法
CN104050745A (zh) 一种基于图像识别的高速硬币清分技术
CN116978834B (zh) 一种用于晶圆生产的智能监测预警系统
CN104483243A (zh) 大米粘连米检测分割方法、装置及系统
WO2022188263A1 (zh) 一种卷烟真伪鉴别装置及方法
CN108510487A (zh) 一种光伏组件远程监测装置
CN106650735A (zh) 一种led字符自动定位识别方法
CN111159411B (zh) 一种融合知识图谱的文本立场分析方法、系统及存储介质
CN112613362A (zh) 一种基于物联网的物品标志识别系统
CN112734637A (zh) 一种导线温度监测的热红外图像处理方法和系统
CN103134757A (zh) 一种基于双目异质机器视觉的检测系统及其检测方法

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21929733

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21929733

Country of ref document: EP

Kind code of ref document: A1